Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 106074
    Prev
    Next
    INDEX
    Explanations

    Suggesting and creating lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compris
    -0.09
     όλ
    -0.08
     horizontal
    -0.08
     arbitrary
    -0.08
     vrije
    -0.08
     proche
    -0.07
     arbitr
    -0.07
     conte
    -0.07
     Dienste
    -0.07
     derog
    -0.07
    POSITIVE LOGITS
     jeweiligen
    0.09
    ਾਨੂੰ
    0.09
    -US
    0.09
    .expected
    0.08
     refrigerators
    0.08
     jeweils
    0.08
     הללו
    0.08
    есу
    0.08
    ಿಸಲಾಗ
    0.08
     abz
    0.08
    Activations Density 0.061%

    No Known Activations